Hendrik/xgboost
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Calculate base_score based on input labels for mae. (#8107)

Browse Source 
Fit an intercept as base score for abs loss.
This commit is contained in:
Jiaming Yuan
2022-09-20 20:53:54 +08:00
committed by GitHub
parent 4f42aa5f12
commit fffb1fca52
42 changed files with 999 additions and 343 deletions
Download Patch File Download Diff File Expand all files Collapse all files

12
src/predictor/cpu_predictor.cc
View File

@@ -429,11 +429,12 @@ class CPUPredictor : public Predictor {
}
out_preds->resize(model.learner_model_param->num_output_group *
(model.param.size_leaf_vector + 1));
auto base_score = model.learner_model_param->BaseScore(ctx_)(0);
// loop over output groups
for (uint32_t gid = 0; gid < model.learner_model_param->num_output_group; ++gid) {
(*out_preds)[gid] = PredValue(inst, model.trees, model.tree_info, gid,
&feat_vecs[0], 0, ntree_limit) +
model.learner_model_param->base_score;
(*out_preds)[gid] =
PredValue(inst, model.trees, model.tree_info, gid, &feat_vecs[0], 0, ntree_limit) +
base_score;
}
}
@@ -504,7 +505,8 @@ class CPUPredictor : public Predictor {
common::ParallelFor(ntree_limit, n_threads, [&](bst_omp_uint i) {
FillNodeMeanValues(model.trees[i].get(), &(mean_values[i]));
});
auto base_margin = info.base_margin_.View(GenericParameter::kCpuId);
auto base_margin = info.base_margin_.View(Context::kCpuId);
auto base_score = model.learner_model_param->BaseScore(Context::kCpuId)(0);
// start collecting the contributions
for (const auto &batch : p_fmat->GetBatches<SparsePage>()) {
auto page = batch.GetView();
@@ -548,7 +550,7 @@ class CPUPredictor : public Predictor {
CHECK_EQ(base_margin.Shape(1), ngroup);
p_contribs[ncolumns - 1] += base_margin(row_idx, gid);
} else {
p_contribs[ncolumns - 1] += model.learner_model_param->base_score;
p_contribs[ncolumns - 1] += base_score;
}
}
});

36
src/predictor/gpu_predictor.cu
View File

@@ -511,7 +511,7 @@ void ExtractPaths(
n = d_nodes[n.Parent() + tree_offset];
path_length++;
}
return PathInfo{int64_t(idx), path_length, tree_idx};
return PathInfo{static_cast<int64_t>(idx), path_length, tree_idx};
});
auto end = thrust::copy_if(
thrust::cuda::par(alloc), nodes_transform,
@@ -859,13 +859,13 @@ class GPUPredictor : public xgboost::Predictor {
// Add the base margin term to last column
p_fmat->Info().base_margin_.SetDevice(ctx_->gpu_id);
const auto margin = p_fmat->Info().base_margin_.Data()->ConstDeviceSpan();
float base_score = model.learner_model_param->base_score;
dh::LaunchN(
p_fmat->Info().num_row_ * model.learner_model_param->num_output_group,
[=] __device__(size_t idx) {
phis[(idx + 1) * contributions_columns - 1] +=
margin.empty() ? base_score : margin[idx];
});
auto base_score = model.learner_model_param->BaseScore(ctx_);
dh::LaunchN(p_fmat->Info().num_row_ * model.learner_model_param->num_output_group,
[=] __device__(size_t idx) {
phis[(idx + 1) * contributions_columns - 1] +=
margin.empty() ? base_score(0) : margin[idx];
});
}
void PredictInteractionContributions(DMatrix* p_fmat,
@@ -918,17 +918,17 @@ class GPUPredictor : public xgboost::Predictor {
// Add the base margin term to last column
p_fmat->Info().base_margin_.SetDevice(ctx_->gpu_id);
const auto margin = p_fmat->Info().base_margin_.Data()->ConstDeviceSpan();
float base_score = model.learner_model_param->base_score;
auto base_score = model.learner_model_param->BaseScore(ctx_);
size_t n_features = model.learner_model_param->num_feature;
dh::LaunchN(
p_fmat->Info().num_row_ * model.learner_model_param->num_output_group,
[=] __device__(size_t idx) {
size_t group = idx % ngroup;
size_t row_idx = idx / ngroup;
phis[gpu_treeshap::IndexPhiInteractions(
row_idx, ngroup, group, n_features, n_features, n_features)] +=
margin.empty() ? base_score : margin[idx];
});
dh::LaunchN(p_fmat->Info().num_row_ * model.learner_model_param->num_output_group,
[=] __device__(size_t idx) {
size_t group = idx % ngroup;
size_t row_idx = idx / ngroup;
phis[gpu_treeshap::IndexPhiInteractions(row_idx, ngroup, group, n_features,
n_features, n_features)] +=
margin.empty() ? base_score(0) : margin[idx];
});
}
void PredictInstance(const SparsePage::Inst&,

7
src/predictor/predictor.cc
View File

@@ -80,14 +80,15 @@ void Predictor::InitOutPredictions(const MetaInfo& info, HostDeviceVector<bst_fl
if (ctx_->gpu_id >= 0) {
out_preds->SetDevice(ctx_->gpu_id);
}
if (base_margin->Size() != 0) {
if (!base_margin->Empty()) {
out_preds->Resize(n);
ValidateBaseMarginShape(info.base_margin_, info.num_row_, n_classes);
out_preds->Copy(*base_margin);
} else {
out_preds->Resize(n);
// cannot rely on the Resize to fill as it might skip if the size is already correct.
out_preds->Fill(model.learner_model_param->base_score);
out_preds->Resize(n);
auto base_score = model.learner_model_param->BaseScore(Context::kCpuId)(0);
out_preds->Fill(base_score);
}
}
} // namespace xgboost